Iwan Kawrakow 45db1385ef iq1_tn: improve AVX2 ...

PP-512 goes to 533 t/s up from 455.
TG-128 @ 2 threads goes to 16.6 t/s up from 14.2.
However, we seem to have a bottleneck somewhere as
TG saturates at 8 threads.

2024-09-09 08:22:24 +03:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Adding iq1_tn - 1.6875 bpw for TriLM ternary models

2024-09-08 17:56:15 +03:00

src

iq1_tn: improve AVX2

2024-09-09 08:22:24 +03:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Merge mainline - Aug 12 2024 (#17)

2024-08-12 15:14:32 +02:00